Indeterminate pulmonary nodules (IPNs) detected on computed tomography (CT) pose challenges because malignancy risk assessment is essential to balance early cancer detection with unnecessary invasive procedures. Artificial intelligence (AI) is increasingly used as a decision-support tool for pulmonary nodule assessment, but its impact on clinicians’ diagnostic and management decisions remains less established than the performance of AI algorithms. This systematic review evaluated the effect of AI assistance on clinicians’ diagnostic and management decisions for CT-detected IPNs. The review followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. PubMed, ScienceDirect, Scopus, and Cochrane Library were searched for studies published from 2015 to 2026. Eligible studies assessed AI-assisted evaluation of indeterminate or suspicious pulmonary nodules on CT, involved clinicians, and reported diagnostic or management outcomes. Five retrospective reader-study or multireader multicase studies were included. AI assistance improved diagnostic performance and malignancy risk stratification. One study reported an AUC increase from 0.82 to 0.89 (P<0.001), with higher sensitivity, specificity, and interobserver agreement (Fleiss κ, 0.35 to 0.58; P<0.001). Another found sensitivity increased from 60% to 98% and specificity from 69% to 99%. Among advanced practice providers, AUC increased from 0.79 to 0.88, while invasive procedure recommendations for malignant nodules increased from 55% to 72%. AI detection also benefited radiologists across experience levels. Standalone AI performed worse than experienced radiologists. AI may improve clinician performance and management decisions, especially as a second-reader tool. Evidence remains limited by retrospective designs, heterogeneous systems and outcomes, and lack of randomized trials; prospective studies are needed.
Copyrights © 2026